Abstract
BACKGROUND: Currently, there is an increasing number of patients reporting dizziness, which has resulted in a positive COVID-19 PCR test. In this paper, we analyzed the ENG signals recorded from patients with a positive COVID-19 PCR test. METHODS: In this paper, both linear and nonlinear analyses of time series were employed to determine the regularity and complexity of a recorded ENG signal. RESULTS: The Wilcoxon rank-sum test indicated that the COVID-19 and non-COVID groups have significant differences based on different extracted features. Various machine learning methods including Linear Discriminant Analysis (LDA), Naïve Base (NB), K-nearest Neighbours (KNN), and Support Vector Machines (SVM) were used to classify COVID-19 and non-COVID groups. The best accuracy, precision and FCR achieved by SVM are 86%, 91% and 0.13. CONCLUSION: In this study, ENG signals were recorded from COVID-19 and control groups. Linear and non-linear features were extracted from the recorded signals to identify significantly different features. Subjects were classified based on SVM and different classifiers. The SVM (polynomial kernel) classifier showed the best result. The proposed method had not been used for the classification of COVID-19 and non-COVID-19 subjects before. This work helps other researchers conduct more research on the development of machine learning methods to diagnose the COVID-19 virus using ENG and other physiological signals.